Algorithm for dynamically tracking and summarizing news events

A dynamic tracking and news technology, applied in the field of multi-document summarization, can solve problems such as redundancy, missing important information, news document mining, etc.

Active Publication Date: 2014-12-03
HEFEI UNIV OF TECH
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Some existing dynamic tracking and summarizing methods of news events only rely on the correlation between query sentences and news documents, and do not fully mine the relevant news documents found, often missing a lot of important information, or generating a lot of redundant information. redundant information, resulting in news summaries that are difficult to summarize or reflect the cause, effect and development of events

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Algorithm for dynamically tracking and summarizing news events
  • Algorithm for dynamically tracking and summarizing news events
  • Algorithm for dynamically tracking and summarizing news events

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] In this embodiment, a dynamic tracking and summarization algorithm of a news event is carried out as follows:

[0073] Step 1. On the search engine, for example, "http: / / news.google.co.in / " under the search engine google news engine, enter the query statement Q related to the news event to retrieve, a query statement is to represent the news The query statement of the event, such as the query statement "MH370", returns several news documents, and uses the crawler tool to crawl and sort the first U news documents and the corresponding release time from the returned several news documents, which respectively constitute the initial return news list X = {x 1 ,x 2 ,...,x i ,...,x U} and the corresponding release time series T={t 1 ,t 2 ,...,t i ,...,t U}, x i Indicates the initial return of the i-th news document in the news list X, t i Indicates that the i-th news document x in the release time series T i The corresponding release time; 1≤i≤U; in this embodiment, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an algorithm for dynamically tracking and summarizing news events. The method is characterized by comprising steps of firstly, inputting query statements related to the news events, retrieving the query statements and acquiring news documents and corresponding release time; secondly, creating word co-occurrence graphs; thirdly, extracting a plurality of themes related to the news events from the word co-occurrence graphs by the aid of a community discovery algorithm; fourthly, selecting sentence group sequences corresponding to each theme in theme sets and corresponding occurrence time labels; fifthly, acquiring abstract sets from the corresponding sentence group sequences for each theme in the theme sets according to occurrence time and generating summaries corresponding to the respective themes. The abstract sets correspond to the respective themes. The algorithm has the advantages that the multiple news themes which are reserved in the found news documents can be sufficiently utilized, each theme is dynamically tracked and summarized, and accordingly users can comprehensively and pertinently understand concerned news abstract.

Description

technical field [0001] The invention belongs to the field of multi-document summarization, and specifically relates to a dynamic tracking and summarization method for dynamic tracking of news events. Background technique [0002] With the rapid development of Internet technology, people's lives are constantly changing. While people use the Internet to obtain more information, they are also troubled by reading many repetitive information every day due to the huge amount of Internet information, resulting in a lot of unnecessary time being wasted. In response to the frequent occurrence of news events on the Internet, users hope to obtain a summary of the development of news events, rather than a lot of related news links. Aiming at news events, according to the time of occurrence, the summary technology of the news is sequentially generated, which is called the dynamic tracking of news events. How to generate a summary of news events based on relevant news documents from a l...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/951
Inventor 吴信东强继朋谢飞
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap